Triple
T36285651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tara Moriarty |
E893073
|
entity |
| Predicate | office held in |
P25590
|
FINISHED |
| Object | New South Wales Government |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: New South Wales Government | Statement: [Tara Moriarty, office held in, New South Wales Government]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: office held in Context triple: [Tara Moriarty, office held in, New South Wales Government]
-
A.
office held level
Indicates the hierarchical level or rank at which an office or position is held within an organizational or governmental structure.
-
B.
officeHeldIn
chosen
Indicates that a particular office or position is held within or associated with a specific geographic or administrative location.
-
C.
officeFounded
Indicates that an office or branch of an organization was established or created at a particular time or place.
-
D.
officeHeldOf
Indicates that a specific office or position is (or was) held by a particular person or entity.
-
E.
officeIsIn
Indicates that one office is located within or inside another specified place or building.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0017dd31d08190aa5e9f72df83733a |
completed | May 10, 2026, 5:30 a.m. |
| PD | Predicate disambiguation | batch_6a0015a1deb88190b9cdaa60455b0a33 |
completed | May 10, 2026, 5:20 a.m. |
Created at: May 3, 2026, 4:09 p.m.